Merge tag 'smp-core-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull SMP updates from Thomas Gleixner:
 "A large update for SMP management:

   - Parallel CPU bringup

     The reason why people are interested in parallel bringup is to
     shorten the (kexec) reboot time of cloud servers to reduce the
     downtime of the VM tenants.

     The current fully serialized bringup does the following per AP:

       1) Prepare callbacks (allocate, intialize, create threads)
       2) Kick the AP alive (e.g. INIT/SIPI on x86)
       3) Wait for the AP to report alive state
       4) Let the AP continue through the atomic bringup
       5) Let the AP run the threaded bringup to full online state

     There are two significant delays:

       #3 The time for an AP to report alive state in start_secondary()
          on x86 has been measured in the range between 350us and 3.5ms
          depending on vendor and CPU type, BIOS microcode size etc.

       #4 The atomic bringup does the microcode update. This has been
          measured to take up to ~8ms on the primary threads depending
          on the microcode patch size to apply.

     On a two socket SKL server with 56 cores (112 threads) the boot CPU
     spends on current mainline about 800ms busy waiting for the APs to
     come up and apply microcode. That's more than 80% of the actual
     onlining procedure.

     This can be reduced significantly by splitting the bringup
     mechanism into two parts:

       1) Run the prepare callbacks and kick the AP alive for each AP
          which needs to be brought up.

          The APs wake up, do their firmware initialization and run the
          low level kernel startup code including microcode loading in
          parallel up to the first synchronization point. (#1 and #2
          above)

       2) Run the rest of the bringup code strictly serialized per CPU
          (#3 - #5 above) as it's done today.

          Parallelizing that stage of the CPU bringup might be possible
          in theory, but it's questionable whether required surgery
          would be justified for a pretty small gain.

     If the system is large enough the first AP is already waiting at
     the first synchronization point when the boot CPU finished the
     wake-up of the last AP. That reduces the AP bringup time on that
     SKL from ~800ms to ~80ms, i.e. by a factor ~10x.

     The actual gain varies wildly depending on the system, CPU,
     microcode patch size and other factors. There are some
     opportunities to reduce the overhead further, but that needs some
     deep surgery in the x86 CPU bringup code.

     For now this is only enabled on x86, but the core functionality
     obviously works for all SMP capable architectures.

   - Enhancements for SMP function call tracing so it is possible to
     locate the scheduling and the actual execution points. That allows
     to measure IPI delivery time precisely"

* tag 'smp-core-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip: (45 commits)
  trace,smp: Add tracepoints for scheduling remotelly called functions
  trace,smp: Add tracepoints around remotelly called functions
  MAINTAINERS: Add CPU HOTPLUG entry
  x86/smpboot: Fix the parallel bringup decision
  x86/realmode: Make stack lock work in trampoline_compat()
  x86/smp: Initialize cpu_primary_thread_mask late
  cpu/hotplug: Fix off by one in cpuhp_bringup_mask()
  x86/apic: Fix use of X{,2}APIC_ENABLE in asm with older binutils
  x86/smpboot/64: Implement arch_cpuhp_init_parallel_bringup() and enable it
  x86/smpboot: Support parallel startup of secondary CPUs
  x86/smpboot: Implement a bit spinlock to protect the realmode stack
  x86/apic: Save the APIC virtual base address
  cpu/hotplug: Allow "parallel" bringup up to CPUHP_BP_KICK_AP_STATE
  x86/apic: Provide cpu_primary_thread mask
  x86/smpboot: Enable split CPU startup
  cpu/hotplug: Provide a split up CPUHP_BRINGUP mechanism
  cpu/hotplug: Reset task stack state in _cpu_up()
  cpu/hotplug: Remove unused state functions
  riscv: Switch to hotplug core state synchronization
  parisc: Switch to hotplug core state synchronization
  ...

14 files changed, 345 insertions, 563 deletions

diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 1328c221af30..6dfecb27b846 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -16,6 +16,7 @@
 #include <asm/cacheflush.h>
 #include <asm/realmode.h>
 #include <asm/hypervisor.h>
+#include <asm/smp.h>
 
 #include <linux/ftrace.h>
 #include "../../realmode/rm/wakeup.h"
@@ -127,7 +128,13 @@ int x86_acpi_suspend_lowlevel(void)
 	 * value is in the actual %rsp register.
 	 */
 	current->thread.sp = (unsigned long)temp_stack + sizeof(temp_stack);
-	smpboot_control = smp_processor_id();
+	/*
+	 * Ensure the CPU knows which one it is when it comes back, if
+	 * it isn't in parallel mode and expected to work that out for
+	 * itself.
+	 */
+	if (!(smpboot_control & STARTUP_PARALLEL_MASK))
+		smpboot_control = smp_processor_id();
 #endif
 	initial_code = (unsigned long)wakeup_long64;
 	saved_magic = 0x123456789abcdef0L;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 770557110051..af49e24b46a4 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -101,6 +101,9 @@ static int apic_extnmi __ro_after_init = APIC_EXTNMI_BSP;
  */
 static bool virt_ext_dest_id __ro_after_init;
 
+/* For parallel bootup. */
+unsigned long apic_mmio_base __ro_after_init;
+
 /*
  * Map cpu index to physical APIC ID
  */
@@ -2163,6 +2166,7 @@ void __init register_lapic_address(unsigned long address)
 
 	if (!x2apic_mode) {
 		set_fixmap_nocache(FIX_APIC_BASE, address);
+		apic_mmio_base = APIC_BASE;
 		apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
 			    APIC_BASE, address);
 	}
@@ -2376,7 +2380,7 @@ static int nr_logical_cpuids = 1;
 /*
  * Used to store mapping between logical CPU IDs and APIC IDs.
  */
-static int cpuid_to_apicid[] = {
+int cpuid_to_apicid[] = {
 	[0 ... NR_CPUS - 1] = -1,
 };
 
@@ -2386,20 +2390,31 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 }
 
 #ifdef CONFIG_SMP
-/**
- * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread
- * @apicid: APIC ID to check
+static void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid)
+{
+	/* Isolate the SMT bit(s) in the APICID and check for 0 */
+	u32 mask = (1U << (fls(smp_num_siblings) - 1)) - 1;
+
+	if (smp_num_siblings == 1 || !(apicid & mask))
+		cpumask_set_cpu(cpu, &__cpu_primary_thread_mask);
+}
+
+/*
+ * Due to the utter mess of CPUID evaluation smp_num_siblings is not valid
+ * during early boot. Initialize the primary thread mask before SMP
+ * bringup.
  */
-bool apic_id_is_primary_thread(unsigned int apicid)
+static int __init smp_init_primary_thread_mask(void)
 {
-	u32 mask;
+	unsigned int cpu;
 
-	if (smp_num_siblings == 1)
-		return true;
-	/* Isolate the SMT bit(s) in the APICID and check for 0 */
-	mask = (1U << (fls(smp_num_siblings) - 1)) - 1;
-	return !(apicid & mask);
+	for (cpu = 0; cpu < nr_logical_cpuids; cpu++)
+		cpu_mark_primary_thread(cpu, cpuid_to_apicid[cpu]);
+	return 0;
 }
+early_initcall(smp_init_primary_thread_mask);
+#else
+static inline void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) { }
 #endif
 
 /*
@@ -2544,6 +2559,9 @@ int generic_processor_info(int apicid, int version)
 	set_cpu_present(cpu, true);
 	num_processors++;
 
+	if (system_state != SYSTEM_BOOTING)
+		cpu_mark_primary_thread(cpu, apicid);
+
 	return cpu;
 }
 
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 22ab13966427..8bb937331acb 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -133,8 +133,8 @@ static bool skip_addr(void *dest)
 	/* Accounts directly */
 	if (dest == ret_from_fork)
 		return true;
-#ifdef CONFIG_HOTPLUG_CPU
-	if (dest == start_cpu0)
+#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_AMD_MEM_ENCRYPT)
+	if (dest == soft_restart_cpu)
 		return true;
 #endif
 #ifdef CONFIG_FUNCTION_TRACER
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 4063e8991211..8f86eacf69f7 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -39,6 +39,8 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 /* Shared L2 cache maps */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map);
 
+static cpumask_var_t cpu_cacheinfo_mask;
+
 /* Kernel controls MTRR and/or PAT MSRs. */
 unsigned int memory_caching_control __ro_after_init;
 
@@ -1172,8 +1174,10 @@ void cache_bp_restore(void)
 		cache_cpu_init();
 }
 
-static int cache_ap_init(unsigned int cpu)
+static int cache_ap_online(unsigned int cpu)
 {
+	cpumask_set_cpu(cpu, cpu_cacheinfo_mask);
+
 	if (!memory_caching_control || get_cache_aps_delayed_init())
 		return 0;
 
@@ -1191,11 +1195,17 @@ static int cache_ap_init(unsigned int cpu)
 	 *      lock to prevent MTRR entry changes
 	 */
 	stop_machine_from_inactive_cpu(cache_rendezvous_handler, NULL,
-				       cpu_callout_mask);
+				       cpu_cacheinfo_mask);
 
 	return 0;
 }
 
+static int cache_ap_offline(unsigned int cpu)
+{
+	cpumask_clear_cpu(cpu, cpu_cacheinfo_mask);
+	return 0;
+}
+
 /*
  * Delayed cache initialization for all AP's
  */
@@ -1210,9 +1220,12 @@ void cache_aps_init(void)
 
 static int __init cache_ap_register(void)
 {
+	zalloc_cpumask_var(&cpu_cacheinfo_mask, GFP_KERNEL);
+	cpumask_set_cpu(smp_processor_id(), cpu_cacheinfo_mask);
+
 	cpuhp_setup_state_nocalls(CPUHP_AP_CACHECTRL_STARTING,
 				  "x86/cachectrl:starting",
-				  cache_ap_init, NULL);
+				  cache_ap_online, cache_ap_offline);
 	return 0;
 }
-core_initcall(cache_ap_register);
+early_initcall(cache_ap_register);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 46ebdd60fd96..8075eb45a3a4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -71,14 +71,6 @@
 
 u32 elf_hwcap2 __read_mostly;
 
-/* all of these masks are initialized in setup_cpu_local_masks() */
-cpumask_var_t cpu_initialized_mask;
-cpumask_var_t cpu_callout_mask;
-cpumask_var_t cpu_callin_mask;
-
-/* representing cpus for which sibling maps can be computed */
-cpumask_var_t cpu_sibling_setup_mask;
-
 /* Number of siblings per CPU package */
 int smp_num_siblings = 1;
 EXPORT_SYMBOL(smp_num_siblings);
@@ -173,15 +165,6 @@ clear_ppin:
 	clear_cpu_cap(c, info->feature);
 }
 
-/* correctly size the local cpu masks */
-void __init setup_cpu_local_masks(void)
-{
-	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
-	alloc_bootmem_cpumask_var(&cpu_callin_mask);
-	alloc_bootmem_cpumask_var(&cpu_callout_mask);
-	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
-}
-
 static void default_init(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_64
@@ -2123,19 +2106,6 @@ static void dbg_restore_debug_regs(void)
 #define dbg_restore_debug_regs()
 #endif /* ! CONFIG_KGDB */
 
-static void wait_for_master_cpu(int cpu)
-{
-#ifdef CONFIG_SMP
-	/*
-	 * wait for ACK from master CPU before continuing
-	 * with AP initialization
-	 */
-	WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask));
-	while (!cpumask_test_cpu(cpu, cpu_callout_mask))
-		cpu_relax();
-#endif
-}
-
 static inline void setup_getcpu(int cpu)
 {
 	unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
@@ -2158,11 +2128,7 @@ static inline void setup_getcpu(int cpu)
 }
 
 #ifdef CONFIG_X86_64
-static inline void ucode_cpu_init(int cpu)
-{
-	if (cpu)
-		load_ucode_ap();
-}
+static inline void ucode_cpu_init(int cpu) { }
 
 static inline void tss_setup_ist(struct tss_struct *tss)
 {
@@ -2239,8 +2205,6 @@ void cpu_init(void)
 	struct task_struct *cur = current;
 	int cpu = raw_smp_processor_id();
 
-	wait_for_master_cpu(cpu);
-
 	ucode_cpu_init(cpu);
 
 #ifdef CONFIG_NUMA
@@ -2291,19 +2255,6 @@ void cpu_init(void)
 	load_fixmap_gdt(cpu);
 }
 
-#ifdef CONFIG_SMP
-void cpu_init_secondary(void)
-{
-	/*
-	 * Relies on the BP having set-up the IDT tables, which are loaded
-	 * on this CPU in cpu_init_exception_handling().
-	 */
-	cpu_init_exception_handling();
-	cpu_init();
-	fpu__init_cpu();
-}
-#endif
-
 #ifdef CONFIG_MICROCODE_LATE_LOADING
 /**
  * store_cpu_caps() - Store a snapshot of CPU capabilities
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 67c8ed99144b..c9318993f959 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -138,20 +138,6 @@ SYM_CODE_START(startup_32)
 	jmp .Ldefault_entry
 SYM_CODE_END(startup_32)
 
-#ifdef CONFIG_HOTPLUG_CPU
-/*
- * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
- * up already except stack. We just set up stack here. Then call
- * start_secondary().
- */
-SYM_FUNC_START(start_cpu0)
-	movl initial_stack, %ecx
-	movl %ecx, %esp
-	call *(initial_code)
-1:	jmp 1b
-SYM_FUNC_END(start_cpu0)
-#endif
-
 /*
  * Non-boot CPU entry point; entered from trampoline.S
  * We can't lgdt here, because lgdt itself uses a data segment, but
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 113c13376e51..c5b9289837dc 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -24,7 +24,9 @@
 #include "../entry/calling.h"
 #include <asm/export.h>
 #include <asm/nospec-branch.h>
+#include <asm/apicdef.h>
 #include <asm/fixmap.h>
+#include <asm/smp.h>
 
 /*
  * We are not able to switch in one step to the final KERNEL ADDRESS SPACE
@@ -234,8 +236,67 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR // above
 
 #ifdef CONFIG_SMP
+	/*
+	 * For parallel boot, the APIC ID is read from the APIC, and then
+	 * used to look up the CPU number.  For booting a single CPU, the
+	 * CPU number is encoded in smpboot_control.
+	 *
+	 * Bit 31	STARTUP_READ_APICID (Read APICID from APIC)
+	 * Bit 0-23	CPU# if STARTUP_xx flags are not set
+	 */
 	movl	smpboot_control(%rip), %ecx
+	testl	$STARTUP_READ_APICID, %ecx
+	jnz	.Lread_apicid
+	/*
+	 * No control bit set, single CPU bringup. CPU number is provided
+	 * in bit 0-23. This is also the boot CPU case (CPU number 0).
+	 */
+	andl	$(~STARTUP_PARALLEL_MASK), %ecx
+	jmp	.Lsetup_cpu
 
+.Lread_apicid:
+	/* Check whether X2APIC mode is already enabled */
+	mov	$MSR_IA32_APICBASE, %ecx
+	rdmsr
+	testl	$X2APIC_ENABLE, %eax
+	jnz	.Lread_apicid_msr
+
+	/* Read the APIC ID from the fix-mapped MMIO space. */
+	movq	apic_mmio_base(%rip), %rcx
+	addq	$APIC_ID, %rcx
+	movl	(%rcx), %eax
+	shr	$24, %eax
+	jmp	.Llookup_AP
+
+.Lread_apicid_msr:
+	mov	$APIC_X2APIC_ID_MSR, %ecx
+	rdmsr
+
+.Llookup_AP:
+	/* EAX contains the APIC ID of the current CPU */
+	xorq	%rcx, %rcx
+	leaq	cpuid_to_apicid(%rip), %rbx
+
+.Lfind_cpunr:
+	cmpl	(%rbx,%rcx,4), %eax
+	jz	.Lsetup_cpu
+	inc	%ecx
+#ifdef CONFIG_FORCE_NR_CPUS
+	cmpl	$NR_CPUS, %ecx
+#else
+	cmpl	nr_cpu_ids(%rip), %ecx
+#endif
+	jb	.Lfind_cpunr
+
+	/*  APIC ID not found in the table. Drop the trampoline lock and bail. */
+	movq	trampoline_lock(%rip), %rax
+	movl	$0, (%rax)
+
+1:	cli
+	hlt
+	jmp	1b
+
+.Lsetup_cpu:
 	/* Get the per cpu offset for the given CPU# which is in ECX */
 	movq	__per_cpu_offset(,%rcx,8), %rdx
 #else
@@ -252,6 +313,16 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	movq	TASK_threadsp(%rax), %rsp
 
 	/*
+	 * Now that this CPU is running on its own stack, drop the realmode
+	 * protection. For the boot CPU the pointer is NULL!
+	 */
+	movq	trampoline_lock(%rip), %rax
+	testq	%rax, %rax
+	jz	.Lsetup_gdt
+	movl	$0, (%rax)
+
+.Lsetup_gdt:
+	/*
 	 * We must switch to a new descriptor in kernel space for the GDT
 	 * because soon the kernel won't have access anymore to the userspace
 	 * addresses where we're currently running on. We have to do that here
@@ -375,13 +446,13 @@ SYM_CODE_END(secondary_startup_64)
 #include "verify_cpu.S"
 #include "sev_verify_cbit.S"
 
-#ifdef CONFIG_HOTPLUG_CPU
+#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_AMD_MEM_ENCRYPT)
 /*
- * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
- * up already except stack. We just set up stack here. Then call
- * start_secondary() via .Ljump_to_C_code.
+ * Entry point for soft restart of a CPU. Invoked from xxx_play_dead() for
+ * restarting the boot CPU or for restarting SEV guest CPUs after CPU hot
+ * unplug. Everything is set up already except the stack.
  */
-SYM_CODE_START(start_cpu0)
+SYM_CODE_START(soft_restart_cpu)
 	ANNOTATE_NOENDBR
 	UNWIND_HINT_END_OF_STACK
 
@@ -390,7 +461,7 @@ SYM_CODE_START(start_cpu0)
 	movq	TASK_threadsp(%rcx), %rsp
 
 	jmp	.Ljump_to_C_code
-SYM_CODE_END(start_cpu0)
+SYM_CODE_END(soft_restart_cpu)
 #endif
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
@@ -433,6 +504,8 @@ SYM_DATA(initial_code,	.quad x86_64_start_kernel)
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 SYM_DATA(initial_vc_handler,	.quad handle_vc_boot_ghcb)
 #endif
+
+SYM_DATA(trampoline_lock, .quad 0);
 	__FINITDATA
 
 	__INIT
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index b031244d6d2d..d095a5d3c14a 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -1328,7 +1328,7 @@ static void sev_es_play_dead(void)
 	 * If we get here, the VCPU was woken up again. Jump to CPU
 	 * startup code to get it back online.
 	 */
-	start_cpu0();
+	soft_restart_cpu();
 }
 #else  /* CONFIG_HOTPLUG_CPU */
 #define sev_es_play_dead	native_play_dead
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 375b33ecafa2..0d54115c3859 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -268,8 +268,7 @@ struct smp_ops smp_ops = {
 #endif
 	.smp_send_reschedule	= native_smp_send_reschedule,
 
-	.cpu_up			= native_cpu_up,
-	.cpu_die		= native_cpu_die,
+	.kick_ap_alive		= native_kick_ap,
 	.cpu_disable		= native_cpu_disable,
 	.play_dead		= native_play_dead,
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 352f0ce1ece4..8de80608fd01 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -57,6 +57,8 @@
 #include <linux/pgtable.h>
 #include <linux/overflow.h>
 #include <linux/stackprotector.h>
+#include <linux/cpuhotplug.h>
+#include <linux/mc146818rtc.h>
 
 #include <asm/acpi.h>
 #include <asm/cacheinfo.h>
@@ -74,7 +76,7 @@
 #include <asm/fpu/api.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
-#include <linux/mc146818rtc.h>
+#include <asm/microcode.h>
 #include <asm/i8259.h>
 #include <asm/misc.h>
 #include <asm/qspinlock.h>
@@ -101,6 +103,12 @@ EXPORT_PER_CPU_SYMBOL(cpu_die_map);
 DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
 
+/* CPUs which are the primary SMT threads */
+struct cpumask __cpu_primary_thread_mask __read_mostly;
+
+/* Representing CPUs for which sibling maps can be computed */
+static cpumask_var_t cpu_sibling_setup_mask;
+
 /* Logical package management. We might want to allocate that dynamically */
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
@@ -121,7 +129,6 @@ int arch_update_cpu_topology(void)
 	return retval;
 }
 
-
 static unsigned int smpboot_warm_reset_vector_count;
 
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
@@ -154,66 +161,59 @@ static inline void smpboot_restore_warm_reset_vector(void)
 
 }
 
-/*
- * Report back to the Boot Processor during boot time or to the caller processor
- * during CPU online.
- */
-static void smp_callin(void)
+/* Run the next set of setup steps for the upcoming CPU */
+static void ap_starting(void)
 {
-	int cpuid;
+	int cpuid = smp_processor_id();
 
 	/*
-	 * If waken up by an INIT in an 82489DX configuration
-	 * cpu_callout_mask guarantees we don't get here before
-	 * an INIT_deassert IPI reaches our local APIC, so it is
-	 * now safe to touch our local APIC.
-	 */
-	cpuid = smp_processor_id();
-
-	/*
-	 * the boot CPU has finished the init stage and is spinning
-	 * on callin_map until we finish. We are free to set up this
-	 * CPU, first the APIC. (this is probably redundant on most
-	 * boards)
+	 * If woken up by an INIT in an 82489DX configuration the alive
+	 * synchronization guarantees that the CPU does not reach this
+	 * point before an INIT_deassert IPI reaches the local APIC, so it
+	 * is now safe to touch the local APIC.
+	 *
+	 * Set up this CPU, first the APIC, which is probably redundant on
+	 * most boards.
 	 */
 	apic_ap_setup();
 
-	/*
-	 * Save our processor parameters. Note: this information
-	 * is needed for clock calibration.
-	 */
+	/* Save the processor parameters. */
 	smp_store_cpu_info(cpuid);
 
 	/*
 	 * The topology information must be up to date before
-	 * calibrate_delay() and notify_cpu_starting().
+	 * notify_cpu_starting().
 	 */
-	set_cpu_sibling_map(raw_smp_processor_id());
+	set_cpu_sibling_map(cpuid);
 
 	ap_init_aperfmperf();
 
-	/*
-	 * Get our bogomips.
-	 * Update loops_per_jiffy in cpu_data. Previous call to
-	 * smp_store_cpu_info() stored a value that is close but not as
-	 * accurate as the value just calculated.
-	 */
-	calibrate_delay();
-	cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy;
 	pr_debug("Stack at about %p\n", &cpuid);
 
 	wmb();
 
+	/*
+	 * This runs the AP through all the cpuhp states to its target
+	 * state CPUHP_ONLINE.
+	 */
 	notify_cpu_starting(cpuid);
+}
 
+static void ap_calibrate_delay(void)
+{
 	/*
-	 * Allow the master to continue.
+	 * Calibrate the delay loop and update loops_per_jiffy in cpu_data.
+	 * smp_store_cpu_info() stored a value that is close but not as
+	 * accurate as the value just calculated.
+	 *
+	 * As this is invoked after the TSC synchronization check,
+	 * calibrate_delay_is_known() will skip the calibration routine
+	 * when TSC is synchronized across sockets.
 	 */
-	cpumask_set_cpu(cpuid, cpu_callin_mask);
+	calibrate_delay();
+	cpu_data(smp_processor_id()).loops_per_jiffy = loops_per_jiffy;
 }
 
-static int cpu0_logical_apicid;
-static int enable_start_cpu0;
 /*
  * Activate a secondary processor.
  */
@@ -226,24 +226,63 @@ static void notrace start_secondary(void *unused)
 	 */
 	cr4_init();
 
-#ifdef CONFIG_X86_32
-	/* switch away from the initial page table */
-	load_cr3(swapper_pg_dir);
-	__flush_tlb_all();
-#endif
-	cpu_init_secondary();
+	/*
+	 * 32-bit specific. 64-bit reaches this code with the correct page
+	 * table established. Yet another historical divergence.
+	 */
+	if (IS_ENABLED(CONFIG_X86_32)) {
+		/* switch away from the initial page table */
+		load_cr3(swapper_pg_dir);
+		__flush_tlb_all();
+	}
+
+	cpu_init_exception_handling();
+
+	/*
+	 * 32-bit systems load the microcode from the ASM startup code for
+	 * historical reasons.
+	 *
+	 * On 64-bit systems load it before reaching the AP alive
+	 * synchronization point below so it is not part of the full per
+	 * CPU serialized bringup part when "parallel" bringup is enabled.
+	 *
+	 * That's even safe when hyperthreading is enabled in the CPU as
+	 * the core code starts the primary threads first and leaves the
+	 * secondary threads waiting for SIPI. Loading microcode on
+	 * physical cores concurrently is a safe operation.
+	 *
+	 * This covers both the Intel specific issue that concurrent
+	 * microcode loading on SMT siblings must be prohibited and the
+	 * vendor independent issue`that microcode loading which changes
+	 * CPUID, MSRs etc. must be strictly serialized to maintain
+	 * software state correctness.
+	 */
+	if (IS_ENABLED(CONFIG_X86_64))
+		load_ucode_ap();
+
+	/*
+	 * Synchronization point with the hotplug core. Sets this CPUs
+	 * synchronization state to ALIVE and spin-waits for the control CPU to
+	 * release this CPU for further bringup.
+	 */
+	cpuhp_ap_sync_alive();
+
+	cpu_init();
+	fpu__init_cpu();
 	rcu_cpu_starting(raw_smp_processor_id());
 	x86_cpuinit.early_percpu_clock_init();
-	smp_callin();
 
-	enable_start_cpu0 = 0;
+	ap_starting();
+
+	/* Check TSC synchronization with the control CPU. */
+	check_tsc_sync_target();
 
-	/* otherwise gcc will move up smp_processor_id before the cpu_init */
-	barrier();
 	/*
-	 * Check TSC synchronization with the boot CPU:
+	 * Calibrate the delay loop after the TSC synchronization check.
+	 * This allows to skip the calibration when TSC is synchronized
+	 * across sockets.
 	 */
-	check_tsc_sync_target();
+	ap_calibrate_delay();
 
 	speculative_store_bypass_ht_init();
 
@@ -257,7 +296,6 @@ static void notrace start_secondary(void *unused)
 	set_cpu_online(smp_processor_id(), true);
 	lapic_online();
 	unlock_vector_lock();
-	cpu_set_state_online(smp_processor_id());
 	x86_platform.nmi_init();
 
 	/* enable local interrupts */
@@ -270,15 +308,6 @@ static void notrace start_secondary(void *unused)
 }
 
 /**
- * topology_is_primary_thread - Check whether CPU is the primary SMT thread
- * @cpu:	CPU to check
- */
-bool topology_is_primary_thread(unsigned int cpu)
-{
-	return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu));
-}
-
-/**
  * topology_smt_supported - Check whether SMT is supported by the CPUs
  */
 bool topology_smt_supported(void)
@@ -288,6 +317,7 @@ bool topology_smt_supported(void)
 
 /**
  * topology_phys_to_logical_pkg - Map a physical package id to a logical
+ * @phys_pkg:	The physical package id to map
  *
  * Returns logical package id or -1 if not found
  */
@@ -304,15 +334,17 @@ int topology_phys_to_logical_pkg(unsigned int phys_pkg)
 	return -1;
 }
 EXPORT_SYMBOL(topology_phys_to_logical_pkg);
+
 /**
  * topology_phys_to_logical_die - Map a physical die id to logical
+ * @die_id:	The physical die id to map
+ * @cur_cpu:	The CPU for which the mapping is done
  *
  * Returns logical die id or -1 if not found
  */
-int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
+static int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
 {
-	int cpu;
-	int proc_id = cpu_data(cur_cpu).phys_proc_id;
+	int cpu, proc_id = cpu_data(cur_cpu).phys_proc_id;
 
 	for_each_possible_cpu(cpu) {
 		struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -323,7 +355,6 @@ int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
 	}
 	return -1;
 }
-EXPORT_SYMBOL(topology_phys_to_logical_die);
 
 /**
  * topology_update_package_map - Update the physical to logical package map
@@ -398,7 +429,7 @@ void smp_store_cpu_info(int id)
 	c->cpu_index = id;
 	/*
 	 * During boot time, CPU0 has this setup already. Save the info when
-	 * bringing up AP or offlined CPU0.
+	 * bringing up an AP.
 	 */
 	identify_secondary_cpu(c);
 	c->initialized = true;
@@ -706,9 +737,9 @@ static void impress_friends(void)
 	 * Allow the user to impress friends.
 	 */
 	pr_debug("Before bogomips\n");
-	for_each_possible_cpu(cpu)
-		if (cpumask_test_cpu(cpu, cpu_callout_mask))
-			bogosum += cpu_data(cpu).loops_per_jiffy;
+	for_each_online_cpu(cpu)
+		bogosum += cpu_data(cpu).loops_per_jiffy;
+
 	pr_info("Total of %d processors activated (%lu.%02lu BogoMIPS)\n",
 		num_online_cpus(),
 		bogosum/(500000/HZ),
@@ -795,51 +826,14 @@ static void __init smp_quirk_init_udelay(void)
 }
 
 /*
- * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
- * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
- * won't ... remember to clear down the APIC, etc later.
+ * Wake up AP by INIT, INIT, STARTUP sequence.
  */
-int
-wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
-{
-	u32 dm = apic->dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
-	unsigned long send_status, accept_status = 0;
-	int maxlvt;
-
-	/* Target chip */
-	/* Boot on the stack */
-	/* Kick the second */
-	apic_icr_write(APIC_DM_NMI | dm, apicid);
-
-	pr_debug("Waiting for send to finish...\n");
-	send_status = safe_apic_wait_icr_idle();
-
-	/*
-	 * Give the other CPU some time to accept the IPI.
-	 */
-	udelay(200);
-	if (APIC_INTEGRATED(boot_cpu_apic_version)) {
-		maxlvt = lapic_get_maxlvt();
-		if (maxlvt > 3)			/* Due to the Pentium erratum 3AP.  */
-			apic_write(APIC_ESR, 0);
-		accept_status = (apic_read(APIC_ESR) & 0xEF);
-	}
-	pr_debug("NMI sent\n");
-
-	if (send_status)
-		pr_err("APIC never delivered???\n");
-	if (accept_status)
-		pr_err("APIC delivery error (%lx)\n", accept_status);
-
-	return (send_status | accept_status);
-}
-
-static int
-wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
+static int wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 {
 	unsigned long send_status = 0, accept_status = 0;
 	int maxlvt, num_starts, j;
 
+	preempt_disable();
 	maxlvt = lapic_get_maxlvt();
 
 	/*
@@ -945,15 +939,16 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 	if (accept_status)
 		pr_err("APIC delivery error (%lx)\n", accept_status);
 
+	preempt_enable();
 	return (send_status | accept_status);
 }
 
 /* reduce the number of lines printed when booting a large cpu count system */
 static void announce_cpu(int cpu, int apicid)
 {
+	static int width, node_width, first = 1;
 	static int current_node = NUMA_NO_NODE;
 	int node = early_cpu_to_node(cpu);
-	static int width, node_width;
 
 	if (!width)
 		width = num_digits(num_possible_cpus()) + 1; /* + '#' sign */
@@ -961,10 +956,10 @@ static void announce_cpu(int cpu, int apicid)
 	if (!node_width)
 		node_width = num_digits(num_possible_nodes()) + 1; /* + '#' */
 
-	if (cpu == 1)
-		printk(KERN_INFO "x86: Booting SMP configuration:\n");
-
 	if (system_state < SYSTEM_RUNNING) {
+		if (first)
+			pr_info("x86: Booting SMP configuration:\n");
+
 		if (node != current_node) {
 			if (current_node > (-1))
 				pr_cont("\n");
@@ -975,77 +970,16 @@ static void announce_cpu(int cpu, int apicid)
 		}
 
 		/* Add padding for the BSP */
-		if (cpu == 1)
+		if (first)
 			pr_cont("%*s", width + 1, " ");
+		first = 0;
 
 		pr_cont("%*s#%d", width - num_digits(cpu), " ", cpu);
-
 	} else
 		pr_info("Booting Node %d Processor %d APIC 0x%x\n",
 			node, cpu, apicid);
 }
 
-static int wakeup_cpu0_nmi(unsigned int cmd, struct pt_regs *regs)
-{
-	int cpu;
-
-	cpu = smp_processor_id();
-	if (cpu == 0 && !cpu_online(cpu) && enable_start_cpu0)
-		return NMI_HANDLED;
-
-	return NMI_DONE;
-}
-
-/*
- * Wake up AP by INIT, INIT, STARTUP sequence.
- *
- * Instead of waiting for STARTUP after INITs, BSP will execute the BIOS
- * boot-strap code which is not a desired behavior for waking up BSP. To
- * void the boot-strap code, wake up CPU0 by NMI instead.
- *
- * This works to wake up soft offlined CPU0 only. If CPU0 is hard offlined
- * (i.e. physically hot removed and then hot added), NMI won't wake it up.
- * We'll change this code in the future to wake up hard offlined CPU0 if
- * real platform and request are available.
- */
-static int
-wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid,
-	       int *cpu0_nmi_registered)
-{
-	int id;
-	int boot_error;
-
-	preempt_disable();
-
-	/*
-	 * Wake up AP by INIT, INIT, STARTUP sequence.
-	 */
-	if (cpu) {
-		boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip);
-		goto out;
-	}
-
-	/*
-	 * Wake up BSP by nmi.
-	 *
-	 * Register a NMI handler to help wake up CPU0.
-	 */
-	boot_error = register_nmi_handler(NMI_LOCAL,
-					  wakeup_cpu0_nmi, 0, "wake_cpu0");
-
-	if (!boot_error) {
-		enable_start_cpu0 = 1;
-		*cpu0_nmi_registered = 1;
-		id = apic->dest_mode_logical ? cpu0_logical_apicid : apicid;
-		boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip);
-	}
-
-out:
-	preempt_enable();
-
-	return boot_error;
-}
-
 int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 {
 	int ret;
@@ -1071,17 +1005,13 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 /*
  * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
  * (ie clustered apic addressing mode), this is a LOGICAL apic ID.
- * Returns zero if CPU booted OK, else error code from
+ * Returns zero if startup was successfully sent, else error code from
  * ->wakeup_secondary_cpu.
  */
-static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
-		       int *cpu0_nmi_registered)
+static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 {
-	/* start_ip had better be page-aligned! */
 	unsigned long start_ip = real_mode_header->trampoline_start;
-
-	unsigned long boot_error = 0;
-	unsigned long timeout;
+	int ret;
 
 #ifdef CONFIG_X86_64
 	/* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */
@@ -1094,7 +1024,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
 	if (IS_ENABLED(CONFIG_X86_32)) {
 		early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu);
 		initial_stack  = idle->thread.sp;
-	} else {
+	} else if (!(smpboot_control & STARTUP_PARALLEL_MASK)) {
 		smpboot_control = cpu;
 	}
 
@@ -1108,7 +1038,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
 	 * This grunge runs the startup process for
 	 * the targeted processor.
 	 */
-
 	if (x86_platform.legacy.warm_reset) {
 
 		pr_debug("Setting warm reset code and vector.\n");
@@ -1123,13 +1052,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
 		}
 	}
 
-	/*
-	 * AP might wait on cpu_callout_mask in cpu_init() with
-	 * cpu_initialized_mask set if previous attempt to online
-	 * it timed-out. Clear cpu_initialized_mask so that after
-	 * INIT/SIPI it could start with a clean state.
-	 */
-	cpumask_clear_cpu(cpu, cpu_initialized_mask);
 	smp_mb();
 
 	/*
@@ -1137,66 +1059,25 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
 	 * - Use a method from the APIC driver if one defined, with wakeup
 	 *   straight to 64-bit mode preferred over wakeup to RM.
 	 * Otherwise,
-	 * - Use an INIT boot APIC message for APs or NMI for BSP.
+	 * - Use an INIT boot APIC message
 	 */
 	if (apic->wakeup_secondary_cpu_64)
-		boot_error = apic->wakeup_secondary_cpu_64(apicid, start_ip);
+		ret = apic->wakeup_secondary_cpu_64(apicid, start_ip);
 	else if (apic->wakeup_secondary_cpu)
-		boot_error = apic->wakeup_secondary_cpu(apicid, start_ip);
+		ret = apic->wakeup_secondary_cpu(apicid, start_ip);
 	else
-		boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
-						     cpu0_nmi_registered);
-
-	if (!boot_error) {
-		/*
-		 * Wait 10s total for first sign of life from AP
-		 */
-		boot_error = -1;
-		timeout = jiffies + 10*HZ;
-		while (time_before(jiffies, timeout)) {
-			if (cpumask_test_cpu(cpu, cpu_initialized_mask)) {
-				/*
-				 * Tell AP to proceed with initialization
-				 */
-				cpumask_set_cpu(cpu, cpu_callout_mask);
-				boot_error = 0;
-				break;
-			}
-			schedule();
-		}
-	}
-
-	if (!boot_error) {
-		/*
-		 * Wait till AP completes initial initialization
-		 */
-		while (!cpumask_test_cpu(cpu, cpu_callin_mask)) {
-			/*
-			 * Allow other tasks to run while we wait for the
-			 * AP to come online. This also gives a chance
-			 * for the MTRR work(triggered by the AP coming online)
-			 * to be completed in the stop machine context.
-			 */
-			schedule();
-		}
-	}
-
-	if (x86_platform.legacy.warm_reset) {
-		/*
-		 * Cleanup possible dangling ends...
-		 */
-		smpboot_restore_warm_reset_vector();
-	}
+		ret = wakeup_secondary_cpu_via_init(apicid, start_ip);
 
-	return boot_error;
+	/* If the wakeup mechanism failed, cleanup the warm reset vector */
+	if (ret)
+		arch_cpuhp_cleanup_kick_cpu(cpu);
+	return ret;
 }
 
-int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
+int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
 {
 	int apicid = apic->cpu_present_to_apicid(cpu);
-	int cpu0_nmi_registered = 0;
-	unsigned long flags;
-	int err, ret = 0;
+	int err;
 
 	lockdep_assert_irqs_enabled();
 
@@ -1210,24 +1091,11 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 	}
 
 	/*
-	 * Already booted CPU?
-	 */
-	if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
-		pr_debug("do_boot_cpu %d Already started\n", cpu);
-		return -ENOSYS;
-	}
-
-	/*
 	 * Save current MTRR state in case it was changed since early boot
 	 * (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync:
 	 */
 	mtrr_save_state();
 
-	/* x86 CPUs take themselves offline, so delayed offline is OK. */
-	err = cpu_check_up_prepare(cpu);
-	if (err && err != -EBUSY)
-		return err;
-
 	/* the FPU context is blank, nobody can own it */
 	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
 
@@ -1235,41 +1103,44 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 	if (err)
 		return err;
 
-	err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered);
-	if (err) {
+	err = do_boot_cpu(apicid, cpu, tidle);
+	if (err)
 		pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
-		ret = -EIO;
-		goto unreg_nmi;
-	}
 
-	/*
-	 * Check TSC synchronization with the AP (keep irqs disabled
-	 * while doing so):
-	 */
-	local_irq_save(flags);
-	check_tsc_sync_source(cpu);
-	local_irq_restore(flags);
+	return err;
+}
 
-	while (!cpu_online(cpu)) {
-		cpu_relax();
-		touch_nmi_watchdog();
-	}
+int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle)
+{
+	return smp_ops.kick_ap_alive(cpu, tidle);
+}
 
-unreg_nmi:
-	/*
-	 * Clean up the nmi handler. Do this after the callin and callout sync
-	 * to avoid impact of possible long unregister time.
-	 */
-	if (cpu0_nmi_registered)
-		unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
+void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu)
+{
+	/* Cleanup possible dangling ends... */
+	if (smp_ops.kick_ap_alive == native_kick_ap && x86_platform.legacy.warm_reset)
+		smpboot_restore_warm_reset_vector();
+}
 
-	return ret;
+void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
+{
+	if (smp_ops.cleanup_dead_cpu)
+		smp_ops.cleanup_dead_cpu(cpu);
+
+	if (system_state == SYSTEM_RUNNING)
+		pr_info("CPU %u is now offline\n", cpu);
+}
+
+void arch_cpuhp_sync_state_poll(void)
+{
+	if (smp_ops.poll_sync_state)
+		smp_ops.poll_sync_state();
 }
 
 /**
- * arch_disable_smp_support() - disables SMP support for x86 at runtime
+ * arch_disable_smp_support() - Disables SMP support for x86 at boottime
  */
-void arch_disable_smp_support(void)
+void __init arch_disable_smp_support(void)
 {
 	disable_ioapic_support();
 }
@@ -1361,14 +1232,6 @@ static void __init smp_cpu_index_default(void)
 	}
 }
 
-static void __init smp_get_logical_apicid(void)
-{
-	if (x2apic_mode)
-		cpu0_logical_apicid = apic_read(APIC_LDR);
-	else
-		cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
-}
-
 void __init smp_prepare_cpus_common(void)
 {
 	unsigned int i;
@@ -1379,7 +1242,6 @@ void __init smp_prepare_cpus_common(void)
 	 * Setup boot CPU information
 	 */
 	smp_store_boot_cpu_info(); /* Final full version of the data */
-	cpumask_copy(cpu_callin_mask, cpumask_of(0));
 	mb();
 
 	for_each_possible_cpu(i) {
@@ -1402,6 +1264,21 @@ void __init smp_prepare_cpus_common(void)
 	set_cpu_sibling_map(0);
 }
 
+#ifdef CONFIG_X86_64
+/* Establish whether parallel bringup can be supported. */
+bool __init arch_cpuhp_init_parallel_bringup(void)
+{
+	if (!x86_cpuinit.parallel_bringup) {
+		pr_info("Parallel CPU startup disabled by the platform\n");
+		return false;
+	}
+
+	smpboot_control = STARTUP_READ_APICID;
+	pr_debug("Parallel CPU startup enabled: 0x%08x\n", smpboot_control);
+	return true;
+}
+#endif
+
 /*
  * Prepare for SMP bootup.
  * @max_cpus: configured maximum number of CPUs, It is a legacy parameter
@@ -1431,8 +1308,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	/* Setup local timer */
 	x86_init.timers.setup_percpu_clockev();
 
-	smp_get_logical_apicid();
-
 	pr_info("CPU0: ");
 	print_cpu_info(&cpu_data(0));
 
@@ -1466,9 +1341,6 @@ void __init native_smp_prepare_boot_cpu(void)
 	if (!IS_ENABLED(CONFIG_SMP))
 		switch_gdt_and_percpu_base(me);
 
-	/* already set me in cpu_online_mask in boot_cpu_init() */
-	cpumask_set_cpu(me, cpu_callout_mask);
-	cpu_set_state_online(me);
 	native_pv_lock_init();
 }
 
@@ -1592,6 +1464,12 @@ __init void prefill_possible_map(void)
 		set_cpu_possible(i, true);
 }
 
+/* correctly size the local cpu masks */
+void __init setup_cpu_local_masks(void)
+{
+	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 
 /* Recompute SMT state for all CPUs on offline */
@@ -1650,10 +1528,6 @@ static void remove_siblinginfo(int cpu)
 static void remove_cpu_from_maps(int cpu)
 {
 	set_cpu_online(cpu, false);
-	cpumask_clear_cpu(cpu, cpu_callout_mask);
-	cpumask_clear_cpu(cpu, cpu_callin_mask);
-	/* was set by cpu_init() */
-	cpumask_clear_cpu(cpu, cpu_initialized_mask);
 	numa_remove_cpu(cpu);
 }
 
@@ -1704,54 +1578,17 @@ int native_cpu_disable(void)
 	return 0;
 }
 
-int common_cpu_die(unsigned int cpu)
-{
-	int ret = 0;
-
-	/* We don't do anything here: idle task is faking death itself. */
-
-	/* They ack this in play_dead() by setting CPU_DEAD */
-	if (cpu_wait_death(cpu, 5)) {
-		if (system_state == SYSTEM_RUNNING)
-			pr_info("CPU %u is now offline\n", cpu);
-	} else {
-		pr_err("CPU %u didn't die...\n", cpu);
-		ret = -1;
-	}
-
-	return ret;
-}
-
-void native_cpu_die(unsigned int cpu)
-{
-	common_cpu_die(cpu);
-}
-
 void play_dead_common(void)
 {
 	idle_task_exit();
 
-	/* Ack it */
-	(void)cpu_report_death();
-
+	cpuhp_ap_report_dead();
 	/*
 	 * With physical CPU hotplug, we should halt the cpu
 	 */
 	local_irq_disable();
 }
 
-/**
- * cond_wakeup_cpu0 - Wake up CPU0 if needed.
- *
- * If NMI wants to wake up CPU0, start CPU0.
- */
-void cond_wakeup_cpu0(void)
-{
-	if (smp_processor_id() == 0 && enable_start_cpu0)
-		start_cpu0();
-}
-EXPORT_SYMBOL_GPL(cond_wakeup_cpu0);
-
 /*
  * We need to flush the caches before going to sleep, lest we have
  * dirty data in our caches when we come back up.
@@ -1819,8 +1656,6 @@ static inline void mwait_play_dead(void)
 		__monitor(mwait_ptr, 0, 0);
 		mb();
 		__mwait(eax, 0);
-
-		cond_wakeup_cpu0();
 	}
 }
 
@@ -1829,11 +1664,8 @@ void __noreturn hlt_play_dead(void)
 	if (__this_cpu_read(cpu_info.x86) >= 4)
 		wbinvd();
 
-	while (1) {
+	while (1)
 		native_halt();
-
-		cond_wakeup_cpu0();
-	}
 }
 
 void native_play_dead(void)
@@ -1852,12 +1684,6 @@ int native_cpu_disable(void)
 	return -ENOSYS;
 }
 
-void native_cpu_die(unsigned int cpu)
-{
-	/* We said "no" in __cpu_disable */
-	BUG();
-}
-
 void native_play_dead(void)
 {
 	BUG();
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 1b83377274b8..ca004e2e4469 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -38,102 +38,12 @@
 static DEFINE_PER_CPU(struct x86_cpu, cpu_devices);
 
 #ifdef CONFIG_HOTPLUG_CPU
-
-#ifdef CONFIG_BOOTPARAM_HOTPLUG_CPU0
-static int cpu0_hotpluggable = 1;
-#else
-static int cpu0_hotpluggable;
-static int __init enable_cpu0_hotplug(char *str)
-{
-	cpu0_hotpluggable = 1;
-	return 1;
-}
-
-__setup("cpu0_hotplug", enable_cpu0_hotplug);
-#endif
-
-#ifdef CONFIG_DEBUG_HOTPLUG_CPU0
-/*
- * This function offlines a CPU as early as possible and allows userspace to
- * boot up without the CPU. The CPU can be onlined back by user after boot.
- *
- * This is only called for debugging CPU offline/online feature.
- */
-int _debug_hotplug_cpu(int cpu, int action)
+int arch_register_cpu(int cpu)
 {
-	int ret;
-
-	if (!cpu_is_hotpluggable(cpu))
-		return -EINVAL;
+	struct x86_cpu *xc = per_cpu_ptr(&cpu_devices, cpu);
 
-	switch (action) {
-	case 0:
-		ret = remove_cpu(cpu);
-		if (!ret)
-			pr_info("DEBUG_HOTPLUG_CPU0: CPU %u is now offline\n", cpu);
-		else
-			pr_debug("Can't offline CPU%d.\n", cpu);
-		break;
-	case 1:
-		ret = add_cpu(cpu);
-		if (ret)
-			pr_debug("Can't online CPU%d.\n", cpu);
-
-		break;
-	default:
-		ret = -EINVAL;
-	}
-
-	return ret;
-}
-
-static int __init debug_hotplug_cpu(void)
-{
-	_debug_hotplug_cpu(0, 0);
-	return 0;
-}
-
-late_initcall_sync(debug_hotplug_cpu);
-#endif /* CONFIG_DEBUG_HOTPLUG_CPU0 */
-
-int arch_register_cpu(int num)
-{
-	struct cpuinfo_x86 *c = &cpu_data(num);
-
-	/*
-	 * Currently CPU0 is only hotpluggable on Intel platforms. Other
-	 * vendors can add hotplug support later.
-	 * Xen PV guests don't support CPU0 hotplug at all.
-	 */
-	if (c->x86_vendor != X86_VENDOR_INTEL ||
-	    cpu_feature_enabled(X86_FEATURE_XENPV))
-		cpu0_hotpluggable = 0;
-
-	/*
-	 * Two known BSP/CPU0 dependencies: Resume from suspend/hibernate
-	 * depends on BSP. PIC interrupts depend on BSP.
-	 *
-	 * If the BSP dependencies are under control, one can tell kernel to
-	 * enable BSP hotplug. This basically adds a control file and
-	 * one can attempt to offline BSP.
-	 */
-	if (num == 0 && cpu0_hotpluggable) {
-		unsigned int irq;
-		/*
-		 * We won't take down the boot processor on i386 if some
-		 * interrupts only are able to be serviced by the BSP in PIC.
-		 */
-		for_each_active_irq(irq) {
-			if (!IO_APIC_IRQ(irq) && irq_has_action(irq)) {
-				cpu0_hotpluggable = 0;
-				break;
-			}
-		}
-	}
-	if (num || cpu0_hotpluggable)
-		per_cpu(cpu_devices, num).cpu.hotpluggable = 1;
-
-	return register_cpu(&per_cpu(cpu_devices, num).cpu, num);
+	xc->cpu.hotpluggable = cpu > 0;
+	return register_cpu(&xc->cpu, cpu);
 }
 EXPORT_SYMBOL(arch_register_cpu);
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 344698852146..1412b771651e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1598,10 +1598,7 @@ void __init tsc_init(void)
 
 #ifdef CONFIG_SMP
 /*
- * If we have a constant TSC and are using the TSC for the delay loop,
- * we can skip clock calibration if another cpu in the same socket has already
- * been calibrated. This assumes that CONSTANT_TSC applies to all
- * cpus in the socket - this should be a safe assumption.
+ * Check whether existing calibration data can be reused.
  */
 unsigned long calibrate_delay_is_known(void)
 {
@@ -1609,6 +1606,21 @@ unsigned long calibrate_delay_is_known(void)
 	int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC);
 	const struct cpumask *mask = topology_core_cpumask(cpu);
 
+	/*
+	 * If TSC has constant frequency and TSC is synchronized across
+	 * sockets then reuse CPU0 calibration.
+	 */
+	if (constant_tsc && !tsc_unstable)
+		return cpu_data(0).loops_per_jiffy;
+
+	/*
+	 * If TSC has constant frequency and TSC is not synchronized across
+	 * sockets and this is not the first CPU in the socket, then reuse
+	 * the calibration value of an already online CPU on that socket.
+	 *
+	 * This assumes that CONSTANT_TSC is consistent for all CPUs in a
+	 * socket.
+	 */
 	if (!constant_tsc || !mask)
 		return 0;
 
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 9452dc9664b5..bbc440c93e08 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -245,7 +245,6 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu)
  */
 static atomic_t start_count;
 static atomic_t stop_count;
-static atomic_t skip_test;
 static atomic_t test_runs;
 
 /*
@@ -344,21 +343,14 @@ static inline unsigned int loop_timeout(int cpu)
 }
 
 /*
- * Source CPU calls into this - it waits for the freshly booted
- * target CPU to arrive and then starts the measurement:
+ * The freshly booted CPU initiates this via an async SMP function call.
  */
-void check_tsc_sync_source(int cpu)
+static void check_tsc_sync_source(void *__cpu)
 {
+	unsigned int cpu = (unsigned long)__cpu;
 	int cpus = 2;
 
 	/*
-	 * No need to check if we already know that the TSC is not
-	 * synchronized or if we have no TSC.
-	 */
-	if (unsynchronized_tsc())
-		return;
-
-	/*
 	 * Set the maximum number of test runs to
 	 *  1 if the CPU does not provide the TSC_ADJUST MSR
 	 *  3 if the MSR is available, so the target can try to adjust
@@ -368,16 +360,9 @@ void check_tsc_sync_source(int cpu)
 	else
 		atomic_set(&test_runs, 3);
 retry:
-	/*
-	 * Wait for the target to start or to skip the test:
-	 */
-	while (atomic_read(&start_count) != cpus - 1) {
-		if (atomic_read(&skip_test) > 0) {
-			atomic_set(&skip_test, 0);
-			return;
-		}
+	/* Wait for the target to start. */
+	while (atomic_read(&start_count) != cpus - 1)
 		cpu_relax();
-	}
 
 	/*
 	 * Trigger the target to continue into the measurement too:
@@ -397,14 +382,14 @@ retry:
 	if (!nr_warps) {
 		atomic_set(&test_runs, 0);
 
-		pr_debug("TSC synchronization [CPU#%d -> CPU#%d]: passed\n",
+		pr_debug("TSC synchronization [CPU#%d -> CPU#%u]: passed\n",
 			smp_processor_id(), cpu);
 
 	} else if (atomic_dec_and_test(&test_runs) || random_warps) {
 		/* Force it to 0 if random warps brought us here */
 		atomic_set(&test_runs, 0);
 
-		pr_warn("TSC synchronization [CPU#%d -> CPU#%d]:\n",
+		pr_warn("TSC synchronization [CPU#%d -> CPU#%u]:\n",
 			smp_processor_id(), cpu);
 		pr_warn("Measured %Ld cycles TSC warp between CPUs, "
 			"turning off TSC clock.\n", max_warp);
@@ -457,11 +442,12 @@ void check_tsc_sync_target(void)
 	 * SoCs the TSC is frequency synchronized, but still the TSC ADJUST
 	 * register might have been wreckaged by the BIOS..
 	 */
-	if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) {
-		atomic_inc(&skip_test);
+	if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable)
 		return;
-	}
 
+	/* Kick the control CPU into the TSC synchronization function */
+	smp_call_function_single(cpumask_first(cpu_online_mask), check_tsc_sync_source,
+				 (unsigned long *)(unsigned long)cpu, 0);
 retry:
 	/*
 	 * Register this CPU's participation and wait for the
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index d82f4fa2f1bf..1da4baa34d1b 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -126,6 +126,7 @@ struct x86_init_ops x86_init __initdata = {
 struct x86_cpuinit_ops x86_cpuinit = {
 	.early_percpu_clock_init	= x86_init_noop,
 	.setup_percpu_clockev		= setup_secondary_APIC_clock,
+	.parallel_bringup		= true,
 };
 
 static void default_nmi_init(void) { };